Charlotte-Mecklenburg MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Charlotte-Mecklenburg MCP Server What's the zoning for 300 South Davidson St?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Charlotte-Mecklenburg MCP Server
An MCP (Model Context Protocol) server that exposes Charlotte, NC and Mecklenburg County open data as tools for an LLM agent. Ask about trash pickup, parcels and zoning, crime and 311 requests, planning areas and rezonings, bike lanes and ADA infrastructure, or environmental data (watersheds, tree canopy, brownfields) at any address in the city/county, and the server geocodes the address and queries the relevant live ArcGIS layer for you.
Core motion behind almost every tool: geocode an address → spatial or attribute query against an ArcGIS REST layer → structured result + a human-readable summary.
Data sources
Everything is queried live, at call time, from public ArcGIS REST endpoints — there
is no local copy of the underlying data (a small local registry of endpoint
metadata, not the data itself, lives in data/registry.json; see "Endpoint
discovery" below). Four backends are in play:
Source | What it is | Base URL |
City of Charlotte on-prem ArcGIS Server | City departmental data (CMPD, sanitation, 311, zoning) |
|
Mecklenburg County on-prem ArcGIS Server | County data (parcels, tax foreclosures) |
|
City of Charlotte ArcGIS Online (AGOL) org | Solid waste routes, bike lanes, ADA infrastructure, CATS transit, watersheds, tree canopy |
|
Mecklenburg County ArcGIS Online (AGOL) org | Capital Improvement Projects, brownfields, battery/HHW recycling sites |
|
All endpoints are public and require no authentication/token. Geocoding uses
Esri's public World geocoder (https://geocode.arcgis.com/...), also token-free for
non-stored results.
An offline registry of ~1,875 discovered service/layer entries across all four
sources (crawled via scripts/build_registry.py) backs the list_datasets tool, so
an agent can search for "what layer has X" before calling a specific tool.
Related MCP server: civic-library-mcp
Install
git clone <this repo> charlotte-mcp
cd charlotte-mcp
uv syncRegister with Claude Code:
claude mcp add charlotte -- uv --directory /Users/dwlavoie/charlotte-mcp run charlotte-mcp(Substitute your actual clone path for /Users/dwlavoie/charlotte-mcp.) The server
runs over stdio — no ports, no API keys, no config needed.
You can also run it directly for local testing:
uv run charlotte-mcpUse from ChatGPT (remote connector)
ChatGPT cannot run local MCP servers — it only supports remote custom connectors (a public HTTPS endpoint, added in Developer Mode). A hosted instance of this server runs at:
https://pcygic2am3.us-east-1.awsapprunner.com/mcpTo connect it (requires ChatGPT Plus/Pro; custom connectors are read-only on those plans, which is all this server needs):
On chatgpt.com, open Settings → Apps & Connectors → Advanced settings and enable Developer mode.
Add a custom connector: name Charlotte City Data, MCP server URL
https://pcygic2am3.us-east-1.awsapprunner.com/mcp, authentication none.Start a new chat, enable the connector from the tools menu, and test with "When is trash pickup at 2437 Remount Rd?" (expected answer: Thursday).
Non-technical users: paste the block below into a new ChatGPT chat and it will walk you through the steps above interactively.
You're going to help me connect a custom connector called "Charlotte City Data" — a read-only tool that answers questions about Charlotte, NC using the city's official open data. Source: https://github.com/Lavoiedavidw/Charlotte-City-MCP Please walk me through, one step at a time, waiting for my confirmation between each: (1) confirm I'm signed in to ChatGPT Plus or Pro on chatgpt.com in a web browser; (2) guide me to Settings → Apps & Connectors → Advanced settings and help me turn on Developer mode; (3) guide me to add a custom connector named "Charlotte City Data" with MCP server URL https://pcygic2am3.us-east-1.awsapprunner.com/mcp and no authentication; (4) have me start a new chat, enable the connector from the tools menu, and test it with "When is trash pickup at 2437 Remount Rd?" — the answer should be Thursday. Afterward, give me five examples of useful things I can ask it about any Charlotte address.
Remote hosting (AWS)
The same server serves streamable HTTP for remote MCP clients:
uv run charlotte-mcp --transport http --host 0.0.0.0 --port 8080The hosted instance is defined as two CloudFormation stacks in infra/:
infra/build.yaml— ECR repository + a CodeBuild project that builds theDockerfiledirectly from this public GitHub repo (no GitHub↔AWS OAuth connection needed) and pushes:latest.infra/service.yaml— an App Runner service (0.25 vCPU / 0.5 GB, ≈$3–5/mo at light usage) serving the image with auto-deploy on new pushes. Deploy it after the first CodeBuild run, since App Runner requires the image to exist.
One transport gotcha, fixed in server.py: FastMCP enables localhost-only DNS
rebinding protection at construction time, which makes a public deployment reject
its own hostname with HTTP 421. The entrypoint disables that protection when
binding to a non-loopback --host.
Tools
21 tools total: 1 geocoder, 1 dataset-discovery tool, and 19 domain tools across six
tool packs. Every location-based tool accepts either address: str or
lat: float, lon: float and returns a dict with a summary field.
Tool | Pack | Description |
| core | Geocode a free-form address to lat/lon via the Esri World geocoder |
| datasets | Search the ~1,875-entry endpoint registry by keyword/source |
| property | Look up a parcel by address, point, PID, or NC-PIN ( |
| property | Get zoning code and rezone date for a parcel ( |
| property | Search county tax foreclosures by neighborhood/zip/status ( |
| sanitation | Garbage/recycling/yard-waste day, provider, route, and GREEN/ORANGE recycling week |
| safety | CMPD patrol + domestic-violence calls-for-service near a point (NPA-aggregate) |
| safety | CMPD violent-offense counts (homicide/rape/robbery/assault) near a point (NPA-aggregate) |
| safety | Point-level homicide incidents near a point, with weapon/clearance detail |
| safety | 311 service requests near a point |
| planning | Named community planning area containing a location |
| planning | Approved rezonings (since 2016) near a point |
| planning | Area plan(s) covering a location |
| transport | Bike lane segments near a point (street, lane type, width, year built) |
| transport | ADA curb ramps, accessible parking, and pedestrian signals near a point |
| transport | County Capital Improvement (stormwater) projects near a point |
| transport | CATS transit capital projects (stations + corridors) near a point |
| environment | Recorded NC Brownfields Program sites near a point |
| environment | Named watershed/basin containing a location |
| environment | Tree canopy / vegetation / impervious-surface stats for a location |
| environment | Household hazardous waste / battery recycling drop-off sites near a point |
Example prompts
"When is trash pickup at 2437 Remount Rd?"
"What's the zoning for 2437 Remount Rd, and has it been rezoned recently?"
"Are there any tax foreclosures in zip code 28208?"
"What watershed is 2437 Remount Rd in, and what's the tree canopy like there?"
"Any 311 requests or CMPD calls for service near 600 E 4th St in the last 90 days?"
"Find bike lanes and ADA curb ramps within 400 meters of 600 E 4th St."
"What capital improvement or CATS transit projects are planned near uptown?"
"Search the dataset registry for anything related to 'waste'."
See docs/demo.md for a full worked transcript of the trash-pickup question.
Known data quirks
City
SWS/AddressLocatorgeocoder is broken — it returns roughly(0, 0)in its native spatial reference (wkid 2264) instead of a real match. The server does not use it;geocodeand every tool's address resolution go through Esri's World geocoder instead.ParcelStatus(county on-prem) rejectsoutFields=*— the layer'squeryoperation returns an HTTP 200 with an ArcGIS{"error": {"code": 400, ...}}body wheneveroutFields=*orresultRecordCountis present, regardless of the where/point/envelope filter.lookup_parcelalways passes an explicit field list and never a page-size hint to work around it. This is isolated to this layer.TaxForeclosures.statusis null on every row in the current dataset (629 total rows checked). Thestatusfilter is still exposed bysearch_tax_foreclosuresas documented — it just won't match anything until the county populates that column.cde_symbology_valandbpo_statusare the actually-populated status-like fields.CMPD_Calls_for_ServiceandViolentCrimeDataare aggregate-only tables, not incident-level data — no geometry, no per-incident rows, just monthly counts by Neighborhood Profile Area (NPA).crime_nearandviolent_crime_nearproxy "near this point" by sampling nearby NPAs from the spatialServiceRequests311layer, then filtering the aggregate tables to those NPAs — a best-effort approximation, not a true point-in-polygon match.homicides_nearandservice_requests_near, by contrast, query real point-level layers directly.ArcGIS
distance+units=esriSRUnit_Meterbuffer overshoot, on some AGOL layers. During development the environment tool pack foundBrownfieldsandBattery_Recycling_Sites(both hosted on layers with a native NC State Plane feet spatial reference) returning features far outside the requested meter radius — consistent with the server silently treating the requested distance as the layer's native unit (feet) instead of converting from meters, a roughly 3.28x overshoot.environment.py'sbrownfields_nearandbattery_recycling_sites_nearwork around this by fetching the full (small: 170 and 5 records respectively) layer once and filtering with a client-side haversine calculation instead of relying on the server-side buffer. A follow-up audit of every other radius-based tool (all ofsafety.pyandtransport.py, plus a re-probe of the two originally-flagged layers) found the meter buffer behaving correctly everywhere else, including on a fresh re-test ofBrownfields/Battery_Recycling_Sites— see the "Task 8 distance-buffer regression check" note inPLAN.mdfor the full methodology and a caution for future maintainers about re-verifying before trusting (or removing a workaround for) the buffer on any new layer.
Development
uv run pytest -m live # live smoke tests against real endpoints, one file per tool packTests are marked live because they hit real network services; expect occasional
transient failures from upstream ArcGIS endpoints rather than code bugs.
Available Tools
21 toolsada_features_nearA
Find ADA pedestrian infrastructure near an address or coordinate.
Covers curb ramps, on-street accessible parking spaces, and accessible pedestrian signals from the city's ADA self-evaluation dataset.
Args: address: Free-form address. Provide this OR lat/lon. lat: Latitude, used with lon instead of address. lon: Longitude, used with lat instead of address. radius_m: Search radius in meters (default 400). feature_type: Which ADA feature types to return: "all" (default), "ramps", "parking", or "signals".
Returns: Dict with the resolved location, lists under "ramps", "parking", and/or "signals" (only the requested types are populated), and a "summary" sentence.
Inputs: lat, lon, address, radius_m, +1 more.
area_plans_atA
Find adopted area/small-area plan boundaries containing a point.
Provide either address (free-form string) or both lat and
lon. Runs a point-in-polygon query against the city's
Area_Plan_Boundaries layer; a point can fall inside more than one
adopted plan boundary (overlapping study areas), so all matches are
returned.
Args:
address: Free-form address, e.g. "2437 Remount Rd, Charlotte, NC".
lat: Latitude, used with lon if address is not given.
lon: Longitude, used with lat if address is not given.
Returns:
Dict with area_plans (list of dicts with plan_name, plan_type,
district, adopt_date, adopt_year, acres, hyperlink),
count, lat, lon, resolved_address, and a summary.
Inputs: lat, lon, address. Returns: object
battery_recycling_sites_nearA
Find battery/household-hazardous-waste recycling drop-off sites near a location.
Queries the Mecklenburg County recycling drop-off centers point layer
(batteries are one of several accepted materials at these sites; there
is no battery-specific kiosk layer published). Provide either
address or both lat/lon.
Args:
address: Free-form address, e.g. "2437 Remount Rd, Charlotte, NC".
lat: Latitude, used with lon if address is not given.
lon: Longitude, used with lat if address is not given.
radius_m: Search radius in meters (default 8000m, ~5 miles — sites
are sparse, only 5 exist countywide).
Returns:
Dict with sites (list of name/address/hours/description/
distance_m), count, lat, lon, resolved_address, and summary.
Inputs: lat, lon, address, radius_m. Returns: object
bike_lanes_nearA
Find bike lanes near an address or coordinate.
Args: address: Free-form address, e.g. "600 E 4th St, Charlotte, NC". Provide this OR lat/lon. lat: Latitude, used with lon instead of address. lon: Longitude, used with lat instead of address. radius_m: Search radius in meters (default 800).
Returns: Dict with the resolved location, a list of bike lane segments (street, lane type, side of street, width, year built, notes), and a "summary" sentence.
Inputs: lat, lon, address, radius_m.
brownfields_nearA
Find recorded brownfield sites within a radius of a location.
Queries the Mecklenburg County recorded brownfields point layer (NC
Brownfields Program). Provide either address or both lat/lon.
Args:
address: Free-form address, e.g. "2437 Remount Rd, Charlotte, NC".
lat: Latitude, used with lon if address is not given.
lon: Longitude, used with lat if address is not given.
radius_m: Search radius in meters (default 1600m, ~1 mile).
Returns:
Dict with brownfields (list of name/status/address/city/acreage/
distance_m), count, lat, lon, resolved_address, and summary.
Inputs: lat, lon, address, radius_m. Returns: object
cats_projects_nearA
Find CATS (Charlotte Area Transit System) capital projects near an address or coordinate.
Queries both the point layer (e.g. stations) and the line layer (e.g. transit corridors/tracks) and merges the results.
Args: address: Free-form address. Provide this OR lat/lon. lat: Latitude, used with lon instead of address. lon: Longitude, used with lat instead of address. radius_m: Search radius in meters (default 1600).
Returns: Dict with the resolved location, a list of CATS projects (name, description, funding status, geometry type), and a "summary".
Inputs: lat, lon, address, radius_m.
cip_projects_nearA
Find Mecklenburg County Capital Improvement Projects (stormwater) near an address or coordinate.
Covers Charlotte-Mecklenburg Storm Water Services projects: drainage improvements, stream & wetland restoration, and pollutant removal — both active and completed.
Args: address: Free-form address. Provide this OR lat/lon. lat: Latitude, used with lon instead of address. lon: Longitude, used with lat instead of address. radius_m: Search radius in meters (default 1600).
Returns: Dict with the resolved location, a list of CIP projects (name, status, phase, type, fiscal-year-complete), and a "summary".
Inputs: lat, lon, address, radius_m.
crime_nearA
CMPD calls-for-service (patrol + domestic violence) near a point.
Provide either address (free-form string) or both lat and
lon. CMPD_Calls_for_Service has no incident-level geometry — it
is a monthly-aggregate table keyed by Neighborhood Profile Area (NPA).
This tool resolves the NPA(s) near the point via nearby 311 request
density (see module docstring), then sums CALL_COUNT by
CALL_DESCRIPTION ("CMPD Patrol Calls For Service" / "CMPD DV Calls
For Service") for months within days of now.
Args:
address: Free-form address, e.g. "600 E 4th St, Charlotte, NC".
lat: Latitude, used with lon if address is not given.
lon: Longitude, used with lat if address is not given.
radius_m: Radius in meters used to resolve nearby NPAs (default 800).
days: Only include months within this many days of now (default 90).
limit: Maximum number of raw NPA/month/category records to return
(default 50); the breakdown totals cover all matching months,
not just the returned records.
Returns:
Dict with nearby_npas (NPA ids used), records (raw NPA/month/
category rows, capped at limit), breakdown (call description ->
total count), total_calls, radius_m, days, lat, lon,
resolved_address, and a summary.
Inputs: lat, lon, days, limit, +2 more. Returns: object
geocodeA
Geocode a free-form address to lat/lon using the Esri World geocoder.
Args: address: Free-form address string, e.g. "2437 Remount Rd, Charlotte, NC".
Returns: Dict with matched address, lat, lon, match score, and a summary.
Inputs: address (required).
get_planning_areaA
Look up the community planning area (and CCW planning region) at a point.
Provide either address (free-form string) or both lat and
lon. Runs a point-in-polygon query against the city's
Community_Planning_Areas layer (one of Charlotte's 15 named
community planning areas, e.g. "West Inner", "Uptown") and the
Center_Corridor_Wedge layer (finer "Center/Corridor/Wedge" planning
region, e.g. "West Corridor").
Args:
address: Free-form address, e.g. "2437 Remount Rd, Charlotte, NC".
lat: Latitude, used with lon if address is not given.
lon: Longitude, used with lat if address is not given.
Returns:
Dict with planning_area (name + equity-index fields, or None if no
polygon covers the point), planning_region (CCW name + location
type, or None), lat, lon, resolved_address, and a
human-readable summary.
Inputs: lat, lon, address. Returns: object
get_trash_scheduleA
Look up garbage, recycling, and yard waste collection schedule.
Provide either address (free-form string) or both lat and
lon. Queries the City of Charlotte Solid Waste Collection polygon
layer via point-in-polygon and returns per-stream day, provider, route,
and (for recycling) the GREEN/ORANGE alternating week parsed from the
route note.
Args:
address: Free-form address, e.g. "2437 Remount Rd, Charlotte, NC".
lat: Latitude, used with lon if address is not given.
lon: Longitude, used with lat if address is not given.
Returns:
Dict with garbage, recycling, yard_waste sub-dicts (each with
day, provider, route, route_note, and for recycling
recycling_week), plus lat, lon, resolved_address, and a
human-readable summary.
Inputs: lat, lon, address. Returns: object
get_zoningA
Get zoning classification for a parcel from Parcel_Zoning_Lookup.
Resolves a parcel (by address, lat/lon, or a known pid) against
ParcelStatus first if a pid isn't supplied directly, then looks
up its zoning record.
Args:
address: Free-form address, e.g. "2437 Remount Rd, Charlotte, NC".
lat: Latitude in decimal degrees (WGS84). Requires lon.
lon: Longitude in decimal degrees (WGS84). Requires lat.
pid: Mecklenburg County parcel ID, if already known.
Returns:
Dict with zoning (dict of zoning attributes or None),
resolved pid, and a summary string.
Inputs: lat, lon, pid, address.
homicides_nearA
Homicide incidents near a point, from the point-level CMPD_Homicide layer.
Provide either address (free-form string) or both lat and
lon. Unlike the aggregate crime tables, CMPD_Homicide is a real
point Feature Layer (public lat/lon per victim, since 2015), so this
runs a genuine point+radius spatial query with a DATE_REPORTED
where-clause. Homicides are rare, so defaults are wider (1600m / 365
days) than the other "near" tools; relax further for sparse areas.
Args:
address: Free-form address, e.g. "600 E 4th St, Charlotte, NC".
lat: Latitude, used with lon if address is not given.
lon: Longitude, used with lat if address is not given.
radius_m: Search radius in meters (default 1600).
days: Only include homicides reported within this many days of now
(default 365).
limit: Maximum number of homicides to return (default 50).
Returns:
Dict with homicides (list of dicts with crime_report_id,
location, weapon, clearance_status, circumstances, ipv,
npa, council_district, patrol_division, date_reported,
clearance_date), count, breakdown (weapon -> count),
radius_m, days, lat, lon, resolved_address, and summary.
Inputs: lat, lon, days, limit, +2 more. Returns: object
list_datasetsA
Search the Charlotte/Mecklenburg ArcGIS endpoint registry.
Use this to discover which layer to query before calling a spatial/attribute tool -- e.g. search "waste" to find the solid waste collection routes layer, or "parcel" for parcel/zoning data.
Args: keyword: Case-insensitive substring matched against service name, layer name, and field names/aliases. Omit to browse. source: Optional filter to one of "city-onprem", "county-onprem", "city-agol", "county-agol". limit: Maximum number of results to return (default 25).
Returns: Dict with a "results" list (service, service_type, layer_name, url, geometry_type, field_count, broken) and a "summary" line.
Inputs: limit, source, keyword. Returns: object
lookup_parcelA
Look up Mecklenburg County parcel(s) from the ParcelStatus layer.
Provide exactly one way to locate the parcel: an address (will
be geocoded), explicit lat/lon, a pid (8-digit parcel
ID), or an nc_pin (NC state parcel identification number).
Args:
address: Free-form address, e.g. "2437 Remount Rd, Charlotte, NC".
lat: Latitude in decimal degrees (WGS84). Requires lon.
lon: Longitude in decimal degrees (WGS84). Requires lat.
pid: Mecklenburg County parcel ID (e.g. "06705133").
nc_pin: NC state parcel identification number (e.g. "4534836016").
Returns:
Dict with parcels (list of parcel attribute dicts), count,
and a summary string.
Inputs: lat, lon, pid, nc_pin, +1 more.
rezonings_nearA
Find approved rezoning petitions near a point.
Provide either address (free-form string) or both lat and
lon. Queries the city's Approved_Rezonings_since_2016__by_CCW
point layer within radius_m meters, filtered to
Decision = 'App' (the layer also carries deferred/withdrawn
petitions despite its name), most recently approved first.
Args:
address: Free-form address, e.g. "2437 Remount Rd, Charlotte, NC".
lat: Latitude, used with lon if address is not given.
lon: Longitude, used with lat if address is not given.
radius_m: Search radius in meters (default 1600, roughly 1 mile).
limit: Maximum number of rezonings to return (default 25).
Returns:
Dict with rezonings (list of dicts with petition, petitioner,
from_zone, to_zone, type, received_date, approved_date,
decision, ccw_region, acres, petition_acres), count,
radius_m, lat, lon, resolved_address, and a summary.
Inputs: lat, lon, limit, address, +1 more. Returns: object
search_tax_foreclosuresA
Search active Mecklenburg County tax foreclosures.
All filters are optional and combined with AND; omit all to list
foreclosures broadly (results are still capped by limit).
nhood matches as a case-insensitive substring; zip and
status match exactly (case-insensitive). Note: as of 2026-07-12
the status field is null on essentially every row in this
dataset, so filtering by it will often return zero rows even when
other filters would match — this is a data-population gap in the
source, not a client bug.
Args: zip: 5-digit ZIP code, e.g. "28208". nhood: Neighborhood/subdivision name substring, e.g. "WESTCHESTER". status: Foreclosure status value, if populated for the record. limit: Max rows to return (default: all matches).
Returns:
Dict with foreclosures (list of property dicts), count,
and a summary string.
Inputs: zip, limit, nhood, status.
service_requests_nearA
311 service requests near a point, from the point-level ServiceRequests311 layer.
Provide either address (free-form string) or both lat and
lon. Runs a point+radius spatial query, most recent first. Note:
this layer has no open/closed "status" field — the closest available
signal is INTERNAL_FIELD_OBSERVATION (a Y/N flag for whether the
request originated from an internal field observation rather than a
resident report), surfaced as field_observation below.
Args:
address: Free-form address, e.g. "600 E 4th St, Charlotte, NC".
lat: Latitude, used with lon if address is not given.
lon: Longitude, used with lat if address is not given.
radius_m: Search radius in meters (default 800).
days: If given, only include requests received within this many
days of now (default None: no date filter).
limit: Maximum number of requests to return (default 50).
Returns:
Dict with requests (list of dicts with request_type, title,
department, division, received_date, field_observation,
address, npa, council_district), count, breakdown
(request_type -> count), radius_m, days, lat, lon,
resolved_address, and summary.
Inputs: lat, lon, days, limit, +2 more. Returns: object
tree_canopy_atA
Get tree canopy stats for the area containing a location.
Point-in-polygon query against the joint City of Charlotte / TreesCharlotte
2022 tree canopy assessment layer, which stacks multiple geography levels
(Neighborhood Profile Area, Council District, Jurisdiction, County, ...)
for the same point. The finest available level is returned as primary
(Neighborhood Profile Area preferred, per plan); all matched levels are
included under by_geography for context. Provide either address or
both lat/lon.
Args:
address: Free-form address, e.g. "2437 Remount Rd, Charlotte, NC".
lat: Latitude, used with lon if address is not given.
lon: Longitude, used with lat if address is not given.
Returns:
Dict with primary (geography/value/canopy_percent/canopy_acres/
vegetation_percent/impervious_percent), by_geography (all matched
levels), lat, lon, resolved_address, and summary.
Inputs: lat, lon, address. Returns: object
violent_crime_nearA
CMPD violent-crime offense counts (Homicide/Rape/Robbery/Assault/...) near a point.
Provide either address (free-form string) or both lat and
lon. Same shape/limitation as crime_near: ViolentCrimeData is a
monthly-aggregate table keyed by Neighborhood Profile Area, not
incident-level points, so nearby NPAs are resolved via 311 density (see
module docstring) and OFFENSE_COUNT is summed by
OFFENSE_DESCRIPTION for months within days of now.
Args:
address: Free-form address, e.g. "600 E 4th St, Charlotte, NC".
lat: Latitude, used with lon if address is not given.
lon: Longitude, used with lat if address is not given.
radius_m: Radius in meters used to resolve nearby NPAs (default 800).
days: Only include months within this many days of now (default 180).
limit: Maximum number of raw NPA/month/offense records to return
(default 50); the breakdown totals cover all matching months.
Returns:
Dict with nearby_npas, records (capped at limit), breakdown
(offense description -> total count), total_offenses, radius_m,
days, lat, lon, resolved_address, and a summary.
Inputs: lat, lon, days, limit, +2 more. Returns: object
watershed_atA
Look up the named watershed/basin containing a location.
Point-in-polygon query against the City of Charlotte "Watershed Basins"
layer, which covers all of Mecklenburg County. Provide either
address or both lat/lon.
Args:
address: Free-form address, e.g. "2437 Remount Rd, Charlotte, NC".
lat: Latitude, used with lon if address is not given.
lon: Longitude, used with lat if address is not given.
Returns:
Dict with watershed (name/tile_name/basin_index), lat, lon,
resolved_address, and summary.
Inputs: lat, lon, address. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 21 tools
Most tools target distinct datasets (parcels, zoning, crime, planning, transportation), but the crime tools (crime_near, violent_crime_near, homicides_near) and planning tools (area_plans_at, get_planning_area) overlap in purpose and could cause misselection. Descriptions are detailed enough to resolve ambiguity.
Names mostly follow a predictable pattern: [subject]_near for radius searches, [subject]_at for point-in-polygon lookups, and verb_noun (get_, lookup_, search_) for direct lookups. Minor deviations exist (geocode, get_planning_area vs area_plans_at) but the mixed conventions are still readable and consistent within their categories.
21 tools is slightly heavy but justified by the wide scope of municipal data (geocoding, parcels, zoning, crime, transit, environment). Each tool covers a distinct dataset, so the count feels appropriate for the server's purpose.
The tool surface covers a broad range of civic data with read-only queries, and list_datasets helps discover additional layers. Minor gaps exist (e.g., no generic query tool for arbitrary layers, no parks or building permits) but agents can work around these for most core workflows.
Maintenance
Related MCP Connectors
MCP server for querying Tulsa County, Oklahoma property and parcel data for AI agents.
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server giving Claude AI access to 22+ NYC public-record databases for real estate due diligence
Agent-native MCP server over 49M+ US public and government records, privacy-first, always current.
Related MCP Servers
- AlicenseAqualityDmaintenanceOpen-source MCP server providing real estate regulatory intelligence (zoning, permits, entitlements, deal scoring) for US properties, enabling AI agents to access 10 callable tools.125 npmMIT
- AlicenseAqualityDmaintenanceAn MCP server that gives AI agents clean, token-efficient access to US civic & property data — geocoding, census tracts, Opportunity Zones, ACS demographics, and FEMA flood zones — sourced entirely from free federal open data.51MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search and query City of Charlotte GIS datasets (parcels, zoning, public works) via ArcGIS Feature Services.88 npm1MIT
- AlicenseAqualityDmaintenanceAn MCP server that gives LLM agents typed, cached access to civic open-data portals via Socrata (SODA 2.1 + Discovery API), enabling search, query, profiling, sampling, and CSV export of datasets.6MIT